Descrizione del progetto
Aiutare l’intelligenza artificiale a decifrare dialoghi complessi
Nel campo dell’IA conversazionale, non è facile decifrare dialoghi non strutturati. Questa difficoltà ostacola lo sviluppo di modelli linguistici affidabili e depurati da pregiudizi. Inoltre, gli assistenti vocali esistenti variano in termini di sofisticazione, creando difficoltà di comprensione e adattabilità in diversi contesti linguistici. In quest’ottica, il progetto ELOQUENCE, finanziato dall’UE, si propone di decodificare dialoghi macchinosi, traducendoli in modelli spiegabili, sicuri e basati sulle conoscenze, favorendo la fiducia e l’affidabilità nelle interazioni guidate dall’IA. Avvalendosi di tecnologie quali l’elaborazione del linguaggio naturale e l’apprendimento automatico, ELOQUENCE svilupperà strutture adattive in grado di imparare da dati limitati per supportare in modo efficiente varie lingue dell’UE. Questo intento ambizioso non solo promuoverà il campo dell’IA conversazionale, ma sosterrà anche i valori europei di inclusività.
Obiettivo
ELOQUENCE is focused on the research and development of innovative technologies for collaborative voice/chat bots. Voice assistant-powered dialogue engines have previously been deployed in a number of commercial and governmental technological pipelines, with a diverse level of complexity. In our concept, such a complexity can be understood as a problem of analysing unstructured dialogues. ELOQUENCE’s key objective is to better comprehend those unstructured dialogues and translate them into explainable, safe, knowledge-grounded, trustworthy and bias-controlled language models. We envision to develop a technology capable of learning by its own, by adapting from a very data-limited corpora to efficiently support most of the EU languages; from a sustainable computational framework to efficient and green-power architectures and, in essence, that may serve as a guidance for all European citizens whilst being respectful and showing the best of our European values, specifically supporting safety-critical applications by involving humans-in-the-loop.
Overall, ELOQUENCE’s project considers building on top and to improve of prior achievements in the domain of conversational agents, e.g. recently launched and public-domain Large Language Models (LLMs), such as chatGPT (e.g. more recent versions), or LaMDa most of them developed in non-EU countries. While including key industrial enterprises from Europe (i.e. Omilia, Telefonica, Synelixis), ELOQUENCE will validate the developed technology through (i) safety-critical scenarios with human-in-the-loop for security-critical applications (i.e. emergency services in call centres) and (ii) smart home assistants via information retrieval and fact-checking against an online knowledge base for lesser risky autonomous systems (i.e. home-assistants). ELOQUENCE will target the R&D of these novel conversational AI technologies in multilingual and multimodal environments and demonstrated in several pilots.
Campo scientifico
Parole chiave
Programma(i)
Meccanismo di finanziamento
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinatore
28050 MADRID
Spagna